Department of Image Processing

A model-based quality improvement and assessment of hazy degraded images

Conference Paper (international conference)

Gabarda S., Cristóbal G., Šroubek Filip

serial: Proceedings of the 15th European Signal Processing Conference

action: EUSIPCO 2007, (Poznan, PL, 03.09.2007-07.09.2007)

research: CEZ:AV0Z10750506

project(s): GA202/05/0242GA ČR

keywords: image fusion, entropy

preview: Download

abstract (eng):

Haze is an atmospheric degradation that appears in real scenarios when there is considerable amount of dust, aerosols or water vapor that impairs the quality of images. The quality improvement procedure is based in a recently developed image fusion methodology consisting in applying a 1-D pseudo-Wigner distribution (PWD) transformation to the source images and on the use of a pixel-wise quality measure. Such procedure is able to process sequences of multi-temporal registered images affected with spatial-variant noise and effectively remove the haze present in the image sequence.

abstract (cze):

Fúze obrazu scén v oparu

RIV: JD